Your Business Technology Events Calendar - Events, News and Networking Since 1998


| Event Details: |
Plan On Attending?  Click Here Bookmark and Share  to Share/Bookmark It!

Wednesday, February 10 2021
3:30am - 5:00am

BayCHI: Monthly meeting: Helping a Robot to Learn from a User Taylor Kessler Faulkner

Monthly meeting: Helping a Robot to Learn from a User 
Taylor Kessler Faulkner


Robots learning in the wild can utilize input from human teachers to improve their learning capabilities. However, people are often imperfect teachers, which can negatively affect learning when the robot expects a teacher to be a constantly present oracle. Towards addressing these issues, we create algorithms for robots learning from imperfect teachers, who may be inattentive to the robot or give inaccurate information. These algorithms are based in Interactive Reinforcement Learning (interactive RL), which enables robots to take information from interactions with both their environmental reward function and additional feedback or advice from their teachers. These algorithms will allow robots to learn with or without human attention and to utilize both correct and incorrect feedback, giving more people the capability to successfully teach a robot.


Taylor Kessler Faulkner is a PhD student and NSF Graduate Research Fellow in the Computer Science Department at the University of Texas at Austin. She works for Prof. Andrea Thomaz in the Socially Intelligent Machines Lab, with work focused on the fields of Human-Robot Interaction and Robot Learning. Specifically, Taylor's research enables robots to learn from inattentive or inaccurate human teachers. Her goal is to create algorithms that allow robots to learn from real people who may not fully understand how robots should complete a task, or have long periods of time available to advise learning robots. 


Plan On Attending? 
Click Here

to Share with Your Network(s) and/or Bookmark It!

Download as iCalendar (iCal) Format For Your Personal Outlook or Mobile Device Calendar!

First Learned About This Event At Please Mention Us When You Register and Attend - Thank You!
All content and formatting Copyright � 1998-2010 -
Event Address:  
City, State or Zip: